04Ecommerce / Retail
A shopping copilot on cleaned catalog embeddings — attribute-aware discovery for ecommerce catalogues.
Timeline · 7 weeks
01Challenge
Shoppers couldn’t find products because search didn’t understand attributes or intent. Catalog data was inconsistent — missing fields, duplicate listings, messy naming.
Merchandising wanted better discovery without a multi-year PIM rewrite.
02Approach
We cleaned and embedded the catalog so attributes like size, material and use-case became searchable signals — not buried text.
A shopping copilot sits on top of that retrieval layer, helping shoppers describe what they want in natural language.
Attribute search and recommendations were wired into the storefront experience the brand already operated.
03Results
Add-to-cart rate rose 12% after launch.
Catalog quality improved enough that search and filters became trustworthy again.
The brand owns the pipeline, embeddings workflow and storefront integration end to end.
04Project details
Deliverables
- Data cleaning & embeddings
- Shopping copilot
- Attribute search
Stack
- OpenAI
- Pinecone
- Shopify
- Next.js
- Industry
- Ecommerce / Retail
- Timeline
- 7 weeks
Related services
- 03Artificial IntelligenceAI applications, conversational agents and automation for enquiries, workflows and repetitive work.
- 04Ecommerce DevelopmentShopify, headless and conversion-focused commerce experiences.
- 05ShopifyShopify design, development, CRO, checkout, SEO, migrations, apps and ongoing support.
- 01AI ApplicationsAI-powered products and features inside new or existing applications.
- 03Shopify Apps & IntegrationsCustom Shopify apps, Admin/Storefront API work and system integrations.
06Contact
Tell us what you need to build or improve.
Share a few project details. You do not need a finished specification to start.